Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in Chinese, such methods are not applicable since words in Chinese require segmentations first. In this paper, we propose a pre-train language model as the substitutes generator using sentence-pieces to craft adversarial examples in Chinese. The substitutions in the generated adversarial examples are not characters or words but \textit{'pieces'}, which are more natural to Chinese readers. Experiments results show that the generated adversarial samples can mislead strong target models and remain fluent and semantically preserved.
Beijing Language and Culture University（北京语言大学）；Tsinghua University（清华大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Beijing Jiaotong University（北京交通大学）
Evaluating Chinese Ambiguity Understanding in Large Language Models
Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）；School of Software Engineering, South China University of Technology（华南理工大学软件学院）
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Alibaba Group（阿里巴巴集团）；Alibaba DAMO Academy（阿里巴巴达摩院）
Chinese pre-trained language models usually process text as a sequence of characters, while ignoring more coarse granularity, e.g., words. In this work, we propose a novel pre-training paradigm for Chinese -- Lattice-BERT, which explicitly incorporates word representations along with characters, thus can model a sentence in a multi-granularity manner. Specifically, we construct a lattice graph from the characters and words in a sentence and feed all these text units into transformers. We design a lattice position attention mechanism to exploit the lattice structures in self-attention layers. W…
To understand what kinds of linguistic knowledge are encoded by pretrained Chinese language models (LMs), we introduce the benchmark of Sino LINGuistics (SLING), which consists of 38K minimal sentence pairs in Mandarin Chinese grouped into 9 high-level linguistic phenomena. Each pair demonstrates the acceptability contrast of a specific syntactic or semantic phenomenon (e.g., The keys are lost vs. The keys is lost), and an LM should assign lower perplexity to the acceptable sentence. In contrast to the CLiMP dataset (Xiang et al., 2021), which also contains Chinese minimal pairs and was create…
Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for these Chinese PLMs remain to be the one provided by Google Chinese Bert \cite{devlin2018bert}, which is based on Chinese characters. Second, the masked language model pre-training is based on a single vocabulary, which limits its downstream task performances. In this work, we first propose a novel method, \emph{seg\_tok}, to form the vocabulary of Chinese BERT, with the help of Chinese word segmentation (CWS) and subwo…
Multi-Criteria Chinese Word Segmentation (MCCWS) aims at finding word boundaries in a Chinese sentence composed of continuous characters while multiple segmentation criteria exist. The unified framework has been widely used in MCCWS and shows its effectiveness. Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework. In this paper, we combine the superiority of the unified framework and pretrained language model, and propose a unified MCCWS model based on BERT. Moreover, we augment the unified BERT-based MCCWS model with the …
GrammarGPT: Exploring Open-Source LLMs for Native Chinese Grammatical Error Correction with Supervised Fine-Tuning
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Soochow University（苏州大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；University of Science and Technology of China（中国科学技术大学）
The pre-trained language models have achieved great successes in various natural language understanding (NLU) tasks due to its capacity to capture the deep contextualized information in text by pre-training on large-scale corpora. In this technical report, we present our practice of pre-training language models named NEZHA (NEural contextualiZed representation for CHinese lAnguage understanding) on Chinese corpora and finetuning for the Chinese NLU tasks. The current version of NEZHA is based on BERT with a collection of proven improvements, which include Functional Relative Positional Encodin…
Hefei University of Technology（合肥工业大学）；Mininglamp Academy of Sciences（明略科学院）
Lexical simplification has attracted much attention in many languages, which is the process of replacing complex words in a given sentence with simpler alternatives of equivalent meaning. Although the richness of vocabulary in Chinese makes the text very difficult to read for children and non-native speakers, there is no research work for Chinese lexical simplification (CLS) task. To circumvent difficulties in acquiring annotations, we manually create the first benchmark dataset for CLS, which can be used for evaluating the lexical simplification systems automatically. In order to acquire more…
EEG2TEXT-CN: An Exploratory Study of Open-Vocabulary Chinese Text-EEG Alignment via Large Language Model and Contrastive Learning on ChineseEEG
Department of Artificial Intelligence in Healthcare, International Academia of Biomedical Innovation Technology（人工智能医疗系，国际生物医学创新技术学院）；National Taiwan University（台湾大学）；Neuro Industry Research, Neuro Industry, Inc.（神经产业研究，神经产业公司）；Department of Biomedical Engineering, University of Southern California（生物医学工程系，南加州大学）；Taiwan Artificial Intelligence Association（台湾人工智能协会）
Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks. While different learning schemes -- fine-tuning, zero-shot, and few-shot learning -- have been widely explored and compared for languages such as English, there is comparatively little work in Chinese to fairly and comprehensively evaluate and compare these methods and thus hinders cumulative progress. In this paper, we introduce the Chinese Few-shot Learning Evaluation Benchmark (FewCLUE), the first comprehensive few-shot evaluation benchmark in Chinese. It includes nine tasks, ranging …
RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongke Fanyu Technology Co., Ltd（中科泛语科技有限公司）
The Chinese language has evolved a lot during the long-term development. Therefore, native speakers now have trouble in reading sentences written in ancient Chinese. In this paper, we propose to build an end-to-end neural model to automatically translate between ancient and contemporary Chinese. However, the existing ancient-contemporary Chinese parallel corpora are not aligned at the sentence level and sentence-aligned corpora are limited, which makes it difficult to train the model. To build the sentence level parallel training data for the model, we propose an unsupervised algorithm that co…
A New Dataset and Empirical Study for Sentence Simplification in Chinese
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, Peking University（北京大学数据科学中心）；The MOE Key Laboratory of Computational Linguistics, Peking University（北京大学计算语言学教育部重点实验室）
Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages. In this paper, we proposed a Cross-Attention Siamese Network (CATsNet) to carry out the task of learning the semantic meanings of Chinese sentences and comparing the similarity between two sentences. This novel model is capable of catching non-local features. Additionally, we also tried to apply the long short-term memory (LSTM) network in the model to improve its performance. The experiments were conducted on the LCQMC dataset and the results showed that our model could ac…
Harbin Institute of Technology（哈尔滨工业大学）；iFLYTEK Research（讯飞研究院）
Existing Chinese text error detection mainly focuses on spelling and simple grammatical errors. These errors have been studied extensively and are relatively simple for humans. On the contrary, Chinese semantic errors are understudied and more complex that humans cannot easily recognize. The task of this paper is Chinese Semantic Error Recognition (CSER), a binary classification task to determine whether a sentence contains semantic errors. The current research has no effective method to solve this task. In this paper, we inherit the model structure of BERT and design several syntax-related pr…
Rapidly developed neural models have achieved competitive performance in Chinese word segmentation (CWS) as their traditional counterparts. However, most of methods encounter the computational inefficiency especially for long sentences because of the increasing model complexity and slower decoders. This paper presents a simple neural segmenter which directly labels the gap existence between adjacent characters to alleviate the existing drawback. Our segmenter is fully end-to-end and capable of performing segmentation very fast. We also show a performance difference with different tag sets. The…
College of Computer and Engineering, Xi’an University of Posts and Telecommunications（西安邮电大学计算机与工程学院）
Chinese medical question-answer matching is more challenging than the open-domain question answer matching in English. Even though the deep learning method has performed well in improving the performance of question answer matching, these methods only focus on the semantic information inside sentences, while ignoring the semantic association between questions and answers, thus resulting in performance deficits. In this paper, we design a series of interactive sentence representation learning models to tackle this problem. To better adapt to Chinese medical question-answer matching and take the…
Underutilization of Syntactic Processing by Chinese Learners of English in Comprehending English Sentences, Evidenced from Adapted Garden-Path Ambiguity Experiment
Yangzhou University（扬州大学）；Hefei University of Technology（合肥工业大学）
Idioms, are a kind of idiomatic expression in Chinese, most of which consist of four Chinese characters. Due to the properties of non-compositionality and metaphorical meaning, Chinese Idioms are hard to be understood by children and non-native speakers. This study proposes a novel task, denoted as Chinese Idiom Paraphrasing (CIP). CIP aims to rephrase idioms-included sentences to non-idiomatic ones under the premise of preserving the original sentence's meaning. Since the sentences without idioms are easier handled by Chinese NLP systems, CIP can be used to pre-process Chinese datasets, there…
Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino-Korean words, which can be converted into corresponding Chinese characters, account for more than fifty of the entire Korean vocabulary. Motivated by this, we propose a simple linguistically motivated solution to improve the performance of the Korean-to-Chinese neural machine translation model by using their common vocabulary. We adopt Chinese characters as a translation pivot by converting Sino-Korean words in Korean sentences to Chinese characters and then train the machin…
Research Center for SCIR, Harbin Institute of Technology（哈尔滨工业大学SCIR研究中心）；State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, China（科大讯飞研究中心认知智能国家重点实验室）；iFLYTEK AI Research (Hebei), Langfang, China（科大讯飞（河北）人工智能研究院，廊坊）
Owing to the continuous efforts by the Chinese NLP community, more and more Chinese machine reading comprehension datasets become available. To add diversity in this area, in this paper, we propose a new task called Sentence Cloze-style Machine Reading Comprehension (SC-MRC). The proposed task aims to fill the right candidate sentence into the passage that has several blanks. We built a Chinese dataset called CMRC 2019 to evaluate the difficulty of the SC-MRC task. Moreover, to add more difficulties, we also made fake candidates that are similar to the correct ones, which requires the machine …
Web-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems are more sensitive to noise than traditional statistical machine translation methods. In this paper, we propose a novel approach to filter out noisy sentence pairs from web-crawled corpora via pre-trained language models. We measure sentence parallelism by leveraging the multilingual capability of BERT and use the Generative Pre-training (GPT) language model as a domain filter to bal…
Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel corpora exist. As described in this paper, we propose a corpus augmentation method by segmenting long sentences in a corpus using back-translation and generating pseudo-parallel sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with Japanese-Chinese scientific paper excerpt corpus (ASPEC-JC) show that the method…
Guizhou University（贵州大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）
A predicate head is a verbal expression that plays a role as the structural center of a sentence. Identifying predicate heads is critical to understanding a sentence. It plays the leading role in organizing the relevant syntactic elements in a sentence, including subject elements, adverbial elements, etc. For some languages, such as English, word morphologies are valuable for identifying predicate heads. However, Chinese offers no morphological information to indicate words` grammatical roles. A Chinese sentence often contains several verbal expressions; identifying the expression that plays t…
East China Normal University（华东师范大学）；Alibaba Group（阿里巴巴集团）；DXY（丁香园）
Machine Reading Comprehension (MRC) aims to extract answers to questions given a passage. It has been widely studied recently, especially in open domains. However, few efforts have been made on closed-domain MRC, mainly due to the lack of large-scale training data. In this paper, we introduce a multi-target MRC task for the medical domain, whose goal is to predict answers to medical questions and the corresponding support sentences from medical information sources simultaneously, in order to ensure the high reliability of medical knowledge serving. A high-quality dataset is manually constructe…
In the scenario of unsupervised extractive summarization, learning high-quality sentence representations is essential to select salient sentences from the input document. Previous studies focus more on employing statistical approaches or pre-trained language models (PLMs) to extract sentence embeddings, while ignoring the rich information inherent in the heterogeneous types of interaction between words and sentences. In this paper, we are the first to propose an unsupervised extractive summarizaiton method with heterogeneous graph embeddings (HGEs) for Chinese document. A heterogeneous text gr…
School of software Engineering, Beijing University of Posts and Telecommunications（北京邮电大学软件学院）；Department of statistics, Harvard University（哈佛大学统计系）
In this paper, we develop a low than character feature embedding called radical embedding, and apply it on LSTM model for sentence segmentation of pre modern Chinese texts. The datasets includes over 150 classical Chinese books from 3 different dynasties and contains different literary styles. LSTM CRF model is a state of art method for the sequence labeling problem. Our new model adds a component of radical embedding, which leads to improved performances. Experimental results based on the aforementioned Chinese books demonstrates a better accuracy than earlier methods on sentence segmentation…
Quantifying patterns of punctuation in modern Chinese prose
Faculty of Computer Science and Telecommunications, Cracow University of Technology（克拉科夫理工大学计算机科学与电信学院）；Institute of Nuclear Physics, Polish Academy of Sciences（波兰科学院核物理研究所）；School of Modern Languages, Georgia Institute of Technology（佐治亚理工学院现代语言学院）
This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7,063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources. Each sentence is corrected by three annotators, and their corrections are carefully reviewed by a senior annotator, resulting in 2.3 references per sentence. We conduct experiments with two mainstream CGEC models, i.e., the sequence-to-sequence model and the sequence-to-edit model, both enhanced with large pretrained language models, achieving competitive benchmark pe…
Chinese meme-face is a special kind of internet subculture widely spread in Chinese Social Community Networks. It usually consists of a template image modified by some amusing details and a text caption. In this paper, we present MemeFaceGenerator, a Generative Adversarial Network with the attention module and template information as supplementary signals, to automatically generate meme-faces from text inputs. We also develop a web service as system demonstration of meme-face synthesis. MemeFaceGenerator has been shown to be capable of generating high-quality meme-faces from random text inputs…
In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information. Previous studies on Chinese SLU do not consider the word information, failing to detect word boundaries that are beneficial for intent detection and slot filling. To address this issue, we propose a multi-level word adapter to inject word information for Chinese SLU, which consists of (1) sentence-level word adapter, which directly fuses the sentence representations of the word information and character information to perform intent detection and (2) character-level word adapter, which is appli…
Tomb biographies of the Tang dynasty provide invaluable information about Chinese history. The original biographies are classical Chinese texts which contain neither word boundaries nor sentence boundaries. Relying on three published books of tomb biographies of the Tang dynasty, we investigated the effectiveness of employing machine-learning methods for algorithmically identifying the pauses and terminals of sentences in the biographies. We consider the segmentation task as a classification problem. Chinese characters that are and are not followed by a punctuation mark are classified into two…
Dependency Grammar has been used by linguists as the basis of the syntactic components of their grammar formalisms. It has also been used in natural language parsing. In China, attempts have been made to use this grammar formalism to parse Chinese sentences using corpus-based techniques. This paper reviews the properties of Dependency Grammar as embodied in four axioms for the well-formedness conditions for dependency structures. It is shown that allowing multiple governors as done by some followers of this formalism is unnecessary. The practice of augmenting Dependency Grammar with functional…
Harbin Institute of Technology（哈尔滨工业大学）；Meituan（美团）
Single online handwritten Chinese character recognition~(single OLHCCR) has achieved prominent performance. However, in real application scenarios, users always write multiple Chinese characters to form one complete sentence and the contextual information within these characters holds the significant potential to improve the accuracy, robustness and efficiency of sentence-level OLHCCR. In this work, we first propose a simple and straightforward end-to-end network, namely vanilla compositional network~(VCN) to tackle the sentence-level OLHCCR. It couples convolutional neural network with sequen…
National Institute of Information and Communications Technology（国立信息通信技术研究所）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Carnegie Mellon University（卡内基梅隆大学）
One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and effective method for recalling previously seen translation examples and incorporating them into the NMT decoding process. Specifically, for an input sentence, we use a search engine to retrieve sentence pairs whose source sides are similar with the input sentence, and then collect $n$-grams that are both in the retrieved target sentences and aligned with words that match in the source sentences, which we call "tra…
Chinese discourse coherence modeling remains a challenge taskin Natural Language Processing field.Existing approaches mostlyfocus on the need for feature engineering, whichadoptthe sophisticated features to capture the logic or syntactic or semantic relationships acrosssentences within a text.In this paper, we present an entity-drivenrecursive deep modelfor the Chinese discourse coherence evaluation based on current English discourse coherenceneural network model. Specifically, to overcome the shortage of identifying the entity(nouns) overlap across sentences in the currentmodel, Our combined …
Bidirectional Chinese and English Passive Sentences Dataset for Machine Translation
Centre de Llenguatge i Computacio (CLiC), Universitat de Barcelona, Spain（巴塞罗那大学语言与计算中心，西班牙）；Institut de Recerca en Sistemes Complexos (UBICS), Universitat de Barcelona, Spain（巴塞罗那大学复杂系统研究中心，西班牙）
Beijing University of Posts and Telecommunications（北京邮电大学）；Brandeis University（布兰迪斯大学）
Pronouns are often dropped in Chinese sentences, and this happens more frequently in conversational genres as their referents can be easily understood from context. Recovering dropped pronouns is essential to applications such as Information Extraction where the referents of these dropped pronouns need to be resolved, or Machine Translation when Chinese is the source language. In this work, we present a novel end-to-end neural network model to recover dropped pronouns in conversational data. Our model is based on a structured attention mechanism that models the referents of dropped pronouns ut…
As a fundamental task in natural language processing, Chinese Grammatical Error Correction (CGEC) has gradually received widespread attention and become a research hotspot. However, one obvious deficiency for the existing CGEC evaluation system is that the evaluation values are significantly influenced by the Chinese word segmentation results or different language models. The evaluation values of the same error correction model can vary considerably under different word segmentation systems or different language models. However, it is expected that these metrics should be independent of the wo…
Lip reading aims at decoding texts from the movement of a speaker's mouth. In recent years, lip reading methods have made great progress for English, at both word-level and sentence-level. Unlike English, however, Chinese Mandarin is a tone-based language and relies on pitches to distinguish lexical or grammatical meaning, which significantly increases the ambiguity for the lip reading task. In this paper, we propose a Cascade Sequence-to-Sequence Model for Chinese Mandarin (CSSMCM) lip reading, which explicitly models tones when predicting sentence. Tones are modeled based on visual informati…
University of Science and Technology of China（中国科学技术大学）；Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）
In this paper, we comprehensively study on context-aware generation of Chinese song lyrics. Conventional text generative models generate a sequence or sentence word by word, failing to consider the contextual relationship between sentences. Taking account into the characteristics of lyrics, a hierarchical attention based Seq2Seq (Sequence-to-Sequence) model is proposed for Chinese lyrics generation. With encoding of word-level and sentence-level contextual information, this model promotes the topic relevance and consistency of generation. A large Chinese lyrics corpus is also leveraged for mod…
Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword because each token is an atomic character. The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters. Such difference motivates us to investigate whether WWM leads to better context understanding ability for Chinese BERT. To achieve this, we introduce two probing tasks related to grammatical error correction and ask pretrained models to revise or insert tokens in…
In this paper we address a method to align English-Chinese bilingual news reports from China News Service, combining both lexical and satistical approaches. Because of the sentential structure differences between English and Chinese, matching at the sentence level as in many other works may result in frequent matching of several sentences en masse. In view of this, the current work also attempts to create shorter alignment pairs by permitting finer matching between clauses from both texts if possible. The current method is based on statiscal correlation between sentence or clause length of bot…
